Borrowing it
Nothing to install: this file belongs to MrBildo/collattice. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MrBildo/collattice/main/CLAUDE.mdgit clone --depth 1 https://github.com/MrBildo/collatticeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/mrbildo/collattice/claude-md)<a href="https://agentmods.dev/instructions/mrbildo/collattice/claude-md"><img src="https://agentmods.dev/badge/instructions/mrbildo/collattice/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/mrbildo/collattice/claude-md"><img src="https://agentmods.dev/badge/instructions/mrbildo/collattice/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.15660 | $0.15660 |
| Opus 5.5 | $0.06264 | $0.06264 |
| Sonnet 5.5 | $0.03132 | $0.03132 |
| Haiku 4.5 | $0.01566 | $0.01566 |
Grade A, and why
collattice CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 566 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collattice
Kanban board web application — .NET Minimal API backend + React SPA frontend. Designed for both human users and AI agent collaboration via MCP tooling.
Repository Rules — Hard
These rules are non-negotiable. They apply to every agent, every dispatch, every commit.
-
.agents/*and.claude/*are permanently gitignored. Local-only. No exceptions. Agent workspaces, dispatch logs, specs, review artifacts, and harness state live here. Nevergit add --forcea path under.agents/*or.claude/*. Not for "preserving review files." Not for "consistency with prior tracked files." Not for any reason. If a reviewer or planner produces an artifact (review doc, brief, spec) inside a worktree's.agents/temp/, copy it OUT to the main repo's.agents/temp/(also gitignored) before cleaning up the worktree. If you find tracked files under these paths, scrub viagit rm --cached -r .agents .claudeon a chore branch and PR to main.Harness gotcha — editing
.claude/*files: the harness Edit/Write tools deny paths under.claude/*(e.g. a local skill file like.claude/skills/release/SKILL.md). This is a built-in Claude Code protection on the.claude/directory (same class as.git/), enforced above the settings allow/deny precedence chain — it is not a project rule and cannot be overridden by apermissions.allowglob. The filesystem allows the write; only the tools refuse. The canonical workaround is shell-level file I/O, which is outside the tool boundary: PowerShell[System.IO.File]::WriteAllText($path, $content)(Windows), or the platform equivalent. For surgical changes to an existing.claude/*file, the Edit tool is friendlier than Write — try it first. This applies to.claude/*only;.agents/*workspace files edit normally through the standard tools. (Investigated card #245.) -
Specs live under
.agents/specs/and are NOT part of the published source. Source code comments must not reference spec documents (e.g.,// per .agents/specs/multi-board.md §6.2) — nor card numbers (// Card #N, bare#N), session or work-item shorthand, or bot-name attributions: none of these are resolvable by an external reader of the published source. Cross-reference internal design via inline rationale (the why, written into the comment) or a full GitHub issue URL (resolvable by anyone). Card numbers, spec paths, and dispatch shorthand belong to internal artifacts — cards, commit messages, dispatch logs — never to shipped source comments. (Collattice publishes its source; this matches the suite-wide source-comment convention now in thedotnet-dev/typescript-devskills.)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +1 lines · +197 tokens per session b01c32fa1bee
- 5d ago Changed · +154 tokens per session 2a2f974f6c00
- 28d ago Changed · +32 lines · +1,651 tokens per session 4e9b5aefd587
- 29d ago Changed · +1 lines · +328 tokens per session 0895571d0138
- 1mo ago Changed · +19 lines · +669 tokens per session 371ff0b1eca6
- 2mo ago First seen · 513 lines · 12,661 tokens per session scan A ac4a3b169c3f
collattice CLAUDE.md is an instructions file published in the GitHub repository MrBildo/collattice (7 stars, last pushed 3d ago), licensed MIT. It adds 15,660 tokens to every session, about $0.0626 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.